Despite the progress in utilizing deep learning to automate chest radiograph interpretation and disease diagnosis tasks, change between sequential Chest X-rays (CXRs) has received limited attention. Monitoring the progression of pathologies that are visualized through chest imaging poses several challenges in anatomical motion estimation and image registration, i.e., spatially aligning the two images and modeling temporal dynamics in change detection. In this work, we propose CheXRelNet, a neural model that can track longitudinal pathology change relations between two CXRs. CheXRelNet incorporates local and global visual features, utilizes inter-image and intra-image anatomical information, and learns dependencies between anatomical region attributes, to accurately predict disease change for a pair of CXRs. Experimental results on the Chest ImaGenome dataset show increased downstream performance compared to baselines. Code is available at https://github.com/PLAN-Lab/ChexRelNet.
This paper details our collaborative approach in capturing a holistic understanding of parental technology use through an assets-based framework. We steer the focus away from the design of technology as the central force of technological innovation, and instead support participants to reflect and describe intimate details that highlight specific use-contexts of technology in their lives. We leverage a group of foreign graduate student mothers' self-described unique strengths to gain an in-depth account of their lived experiences with technology. As research participants and co-authors, our collaborators elicit intimate narratives about meaningful events in their lives, bringing social and cultural aspects of their lived experience to the forefront, and thus providing broader context of their use of technology. We detail and reflect upon our approach of promoting user agency by creating an affinity group, fostering a safe and intimate space for research engagement, and describe the implications of using our adapted research methodology in intimate settings. We conclude by highlighting the various ways in which technology facilitates foreign student parenting, as well as the ways in which it serves as a temporary band-aid solution, prompting consideration of larger social issues.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.